© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 16050
    Prev
    Next
    INDEX
    Explanations

    compact design

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fully
    -0.21
    /or
    -0.19
    /OR
    -0.19
    etak
    -0.18
    imet
    -0.18
    /her
    -0.17
    abama
    -0.17
    ä¸Ģéģį
    -0.17
    erk
    -0.17
    bery
    -0.16
    POSITIVE LOGITS
    ness
    0.33
    -minded
    0.32
     minded
    0.25
    ãģĹãĤĩãģĨ
    0.21
    eur
    0.20
    äºĨ许å¤ļ
    0.20
    åĮĸçļĦ
    0.19
    ly
    0.19
    ity
    0.19
    ï¸ı
    0.19
    Activations Density 0.007%

    No Known Activations